Flow Regime Identification for Wet Gas Flow Based on Kurtosis Feature of Flow-Induced Pipeline Vibration

Abstract:

Flow-induced vibration occurs widely in flow pipelines, and pipeline vibration signals have various frequency characteristics corresponding to different flow regimes. Therefore, an novel noninvasive approach to flow regime identification for wet gas flow in a horizontal pipeline is presented in this paper. The vibration signals were collected by a transducer installed on external wall of pipeline. Empirical mode decomposition (EMD) was used to decompose the vibration signal into different intrinsic mode functions (IMFs), and then the kurtosis of each IMF component for each experimental data was calculated. Finally, the IMF kurtosis feature vector was input to the support vector machine (SVM) to identify three typical flow regimes for wet gas flow including stratified/stratified wavy flow, annular/annular mist flow and slug flow in a horizontal pipeline 50 mm in diameter. The experimental results show that the proposed approach can identify flow regimes effectively, and the identification rate is 80.6%.

• Periodical: Applied Mechanics and Materials (Volume 527)
• Pages: 49-52
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.527.49
• Online since: February 2014
• Authors: Chen Quan Hua*, Hua Wei Pan, Yan Feng Geng, Lan Chang Xing
• Keywords: Empirical Mode Decomposition (EMD), Flow Regime Identification, Flow-Induced Vibration, Kurtosis, Support Vector Machine (SVM), Wet Gas Flow

References

[1] Hiroaki Matsubara, Kiyoshi Naito. Effect of liquid viscosity on flow patterns of gas-liquid two-phase flow in a horizontal pipe [J]. 2011, 37(10): 1277-1281.

DOI: 10.1016/j.ijmultiphaseflow.2011.08.001

[2] Chenquan Hua, Yanfeng Geng. Wet gas meter based on the vortex precession frequency and differential pressure combination of swirlmeter [J]. 2012, 45(4): 763-768.

DOI: 10.1016/j.measurement.2011.12.013

[3] Blevins RD. Flow-induced vibration [J]. (1990).

[4] J.M. Mandhane, G.A. Gregory, K. Aziz. A flow pattern map for gas-liquid flow in horizontal pipes [J]. 1974, 1(4): 537-553.

DOI: 10.1016/0301-9322(74)90006-8

[5] Bin Sun, Hongjian Zhang, Lu Cheng, et al. Flow regime identification of gas-liquid two-phase flow based on HHT[J]. Chinese Journal of Chemical Engineering, 2006, 14(1): 24-30.

DOI: 10.1016/s1004-9541(06)60033-5

[6] Huang N E, Shen Z, Long S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis [J]. 1998, 454(1971): 903-995.

DOI: 10.1098/rspa.1998.0193

[7] Cortes C, Vapnik V. Support-vector networks [J]. Machine learning, 1995, 20(3): 273-297.

DOI: 10.1007/bf00994018

[8] Chih-Chung Chang, Chih-Jen Lin. LIBSVM: a library for support vector machines [J]. 2011, 2(3): 27.